Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the user guide for the big picture.

8.6.4. nilearn.input_data.NiftiMapsMasker

class nilearn.input_data.NiftiMapsMasker(maps_img, mask_img=None, allow_overlap=True, smoothing_fwhm=None, standardize=False, detrend=False, low_pass=None, high_pass=None, t_r=None, dtype=None, resampling_target='data', memory=Memory(location=None), memory_level=0, verbose=0)

Class for masking of Niimg-like objects.

NiftiMapsMasker is useful when data from overlapping volumes should be extracted (contrarily to NiftiLabelsMasker). Use case: Summarize brain signals from large-scale networks obtained by prior PCA or ICA.

Note that, Inf or NaN present in the given input images are automatically put to zero rather than considered as missing data.

Parameters:

maps_img: 4D niimg-like object

See http://nilearn.github.io/manipulating_images/input_output.html Set of continuous maps. One representative time course per map is extracted using least square regression.

mask_img: 3D niimg-like object, optional

See http://nilearn.github.io/manipulating_images/input_output.html Mask to apply to regions before extracting signals.

allow_overlap: boolean, optional

If False, an error is raised if the maps overlaps (ie at least two maps have a non-zero value for the same voxel). Default is True.

smoothing_fwhm: float, optional

If smoothing_fwhm is not None, it gives the full-width half maximum in millimeters of the spatial smoothing to apply to the signal.

standardize: {‘zscore’, ‘psc’, True, False}, default is ‘zscore’

Strategy to standardize the signal. ‘zscore’: the signal is z-scored. Timeseries are shifted to zero mean and scaled to unit variance. ‘psc’: Timeseries are shifted to zero mean value and scaled to percent signal change (as compared to original mean signal). True : the signal is z-scored. Timeseries are shifted to zero mean and scaled to unit variance. False : Do not standardize the data.

detrend: boolean, optional

This parameter is passed to signal.clean. Please see the related documentation for details

low_pass: None or float, optional

This parameter is passed to signal.clean. Please see the related documentation for details

high_pass: None or float, optional

This parameter is passed to signal.clean. Please see the related documentation for details

t_r: float, optional

This parameter is passed to signal.clean. Please see the related documentation for details

dtype: {dtype, “auto”}

Data type toward which the data should be converted. If “auto”, the data will be converted to int32 if dtype is discrete and float32 if it is continuous.

resampling_target: {“mask”, “maps”, “data”, None} optional.

Gives which image gives the final shape/size. For example, if resampling_target is “mask” then maps_img and images provided to fit() are resampled to the shape and affine of mask_img. “None” means no resampling: if shapes and affines do not match, a ValueError is raised. Default value: “data”.

memory: joblib.Memory or str, optional

Used to cache the region extraction process. By default, no caching is done. If a string is given, it is the path to the caching directory.

memory_level: int, optional

Aggressiveness of memory caching. The higher the number, the higher the number of functions that will be cached. Zero means no caching.

verbose: integer, optional

Indicate the level of verbosity. By default, nothing is printed

See also

nilearn.input_data.NiftiMasker, nilearn.input_data.NiftiLabelsMasker

Notes

If resampling_target is set to “maps”, every 3D image processed by transform() will be resampled to the shape of maps_img. It may lead to a very large memory consumption if the voxel number in maps_img is large.

__init__(maps_img, mask_img=None, allow_overlap=True, smoothing_fwhm=None, standardize=False, detrend=False, low_pass=None, high_pass=None, t_r=None, dtype=None, resampling_target='data', memory=Memory(location=None), memory_level=0, verbose=0)

Initialize self. See help(type(self)) for accurate signature.

fit(X=None, y=None)

Prepare signal extraction from regions.

All parameters are unused, they are for scikit-learn compatibility.

fit_transform(imgs, confounds=None)

Prepare and perform signal extraction.

get_params(deep=True)

Get parameters for this estimator.

Parameters:

deep : bool, default=True

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

params : mapping of string to any

Parameter names mapped to their values.

inverse_transform(region_signals)

Compute voxel signals from region signals

Any mask given at initialization is taken into account.

Parameters:

region_signals: 2D numpy.ndarray

Signal for each region. shape: (number of scans, number of regions)

Returns:

voxel_signals: nibabel.Nifti1Image

Signal for each voxel. shape: that of maps.

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as pipelines). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**params : dict

Estimator parameters.

Returns:

self : object

Estimator instance.

transform(imgs, confounds=None)

Apply mask, spatial and temporal preprocessing

Parameters:

imgs: 3D/4D Niimg-like object

See http://nilearn.github.io/manipulating_images/input_output.html Images to process. It must boil down to a 4D image with scans number as last dimension.

confounds: CSV file or array-like, optional

This parameter is passed to signal.clean. Please see the related documentation for details. shape: (number of scans, number of confounds)

Returns:

region_signals: 2D numpy.ndarray

Signal for each element. shape: (number of scans, number of elements)

transform_single_imgs(imgs, confounds=None)

Extract signals from a single 4D niimg.

Parameters:

imgs: 3D/4D Niimg-like object

See http://nilearn.github.io/manipulating_images/input_output.html Images to process. It must boil down to a 4D image with scans number as last dimension.

confounds: CSV file or array-like, optional

This parameter is passed to signal.clean. Please see the related documentation for details. shape: (number of scans, number of confounds)

Returns:

region_signals: 2D numpy.ndarray

Signal for each map. shape: (number of scans, number of maps)